CN104901827A - Network resource evaluation method and device based on user business structure - Google Patents
Network resource evaluation method and device based on user business structure Download PDFInfo
- Publication number
- CN104901827A CN104901827A CN201410086165.5A CN201410086165A CN104901827A CN 104901827 A CN104901827 A CN 104901827A CN 201410086165 A CN201410086165 A CN 201410086165A CN 104901827 A CN104901827 A CN 104901827A
- Authority
- CN
- China
- Prior art keywords
- data
- customer service
- sample
- network resource
- assessed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses a network resource evaluation method based on a user business structure. The method comprises the following steps: acquiring sample data of a sample area; screening qualified sample data according to a network index, and modeling the qualified sample data with a mathematic modeling algorithm to obtain a data model between network resources and the user business structure; and acquiring user business structure data of an area to be evaluated, and introducing the user business structure data of the area to be evaluated into the data model to obtain network resource data needed by the area to be evaluated. The invention also discloses a network resource evaluation device based on the user business structure.
Description
Technical field
The present invention relates to network resource evaluation technology, particularly relate to a kind of network resource evaluation method based on customer service structure and device.
Background technology
At present, along with the fast development of mobile Internet, various emerging service constantly emerges, and user is no longer confined to speech business for the perception of mobile communications network.In the mobile Internet epoch, the user of mobile terminal perception of surfing the Net becomes the key factor affecting user satisfaction, how to eliminate the resource bottleneck of network end-to-end, ensures that user data service resource requirement is the basis promoting user satisfaction.Wherein, the relation between user, flow, business, terminal, pipeline is intricate, and how comprehensive consideration, each factor of quantitative evaluation ensure the basic place of user awareness just on the impact of network resource consumption.
Prior art one: operator adopts by the prediction to telephone traffic, data traffic and number of users often carrying out the network planning, networking to network, goes to calculate the resource distribution needed for disparate networks and scale.Particularly, when realizing the network planning, in units of year, first gathering the data such as network traffic, data traffic, number of users several years ago, then carried out the assessment of Internet resources by year-on-year growth rate method, unit telephone traffic method, curve-fitting method etc.
But on the one hand, in the mobile Internet epoch, the consumption of various emerging service to Internet resources is more outstanding, consider that the traditional resource appraisal procedure of number of users and flow can not be suitable for for this.The factor such as intelligent terminal, instant messaging service has a strong impact on the consumption to Internet resources, therefore, also needs badly carry out statistical analysis to these factors when assessing Internet resources.On the other hand, for the short-term such as festivals or holidays, specific activity, accident, traditional network resource evaluation method effectively cannot realize the accurate predicting and evaluating of Internet resources.
Prior art two: a kind of carrying out for wireless network resource assesses the method optimized, and the method, by carrying out statistical analysis to the internet behavior record of each resident user in community to be optimized, obtains the flow of game, video traffic in community to be optimized; When the game in community, video traffic flow exceed certain threshold value, by the mode of newly-built WIFI website, network is optimized.
But, can only process event in the program, effective predicting and evaluating cannot be carried out to the development of business.
Prior art three: a kind of method relying on equipment performance index to carry out wireless network resource optimization, in the method, network management entity according to administrative each service area or each community speech business in one-period periodically counted if R4 business and downloading service are as the traffic carrying capacity of HSDPA business, or according to the resource adjustment request that base station (NodeB) sends, generate resource adjustment instruction and be issued to the NodeB needing to carry out belonging to the community of resource distribution adjustment; NodeB, according to reception resource adjustment instruction, adjusts the Network resource allocation of respective cell.
But the method can only come into force when equipment performance index changes, and does not have the predictability of stock assessment.In addition, the method effectively cannot adjust other Internet resources beyond wireless network, as general packet radio service technology (General Packet Radio Service, GPRS) serving GPRS support node (Serving GPRS Support Node, SGSN) attachment, Gateway GPRS Support Node (Gateway GPRS Support Node, GGSN) packet data protocol (Packet Data Protocol, PDP) number, WAP (wireless access protocol) (Wireless Application Protocol, WAP) gateway online user number etc. is activated.
Therefore, because mobile Internet is compared with legacy network, the behavior model of user there occurs basic change, and existing above-mentioned network resource evaluation method is all not enough to accurate evaluation goes out the Expenditure Levels of user behavior to Internet resources; Usually, the duration, intelligent terminal Signalling exchange etc. that use of the frequency of online, business all can produce resource consumption in various degree to network.
Summary of the invention
In view of this, the embodiment of the present invention is expected to provide a kind of network resource evaluation method based on customer service structure and device, can realize the accurate evaluation to network resource consumption, and then improves resource utilization.
For achieving the above object, technical scheme of the present invention is achieved in that
Embodiments provide a kind of network resource evaluation method based on customer service structure, the method comprises:
Obtain the sample data of sample areas;
Filter out qualified sample data according to network index, utilize mathematical modelling algorithm to carry out modeling described qualified sample data, obtain the data model between Internet resources and customer service structure;
Gather the customer service structured data in region to be assessed, bring the customer service structured data in described region to be assessed into described data model, draw the network resource data needed for described region to be assessed.
In such scheme, the sample data of described acquisition sample areas comprises:
To set granularity in units of the period, add up the network resource data that described customer service structured data, quality of service index related data and the described sample areas set in period sample areas is corresponding.
In such scheme, describedly screen qualified sample data according to network index and comprise: in the sample data of described sample areas, screening quality of service index is in zone of reasonableness, is positioned at the sample data set before percentage without line use ratio and Packet Data Channel PDCH load-carrying efficiency from high to low.
In such scheme, described mathematical modelling algorithm is multivariate regression algorithm.
In such scheme, the customer service structured data in described collection region to be assessed comprises: treat assessment area by Gn signalling analysis system and carry out customer service structured data statistics or the customer service structured data by historical data analysis prediction community future.
The embodiment of the present invention additionally provides a kind of network resource evaluation device based on customer service structure, and this device comprises: data capture unit, screening unit, modeling unit, data acquisition unit and computing unit; Wherein,
Described data capture unit, for obtaining the sample data of sample areas;
Described screening unit, for filtering out qualified sample data according to network index;
Described modeling unit, for utilizing mathematical modelling algorithm to carry out modeling qualified sample data, obtains the data model between Internet resources and customer service structure;
Described data acquisition unit, for gathering the customer service structured data in region to be assessed;
Described computing unit, brings the customer service structured data in described region to be assessed into described data model, draws the network resource data needed for described region to be assessed.
In such scheme, described data capture unit, to set granularity in units of the period, adds up the network resource data that described customer service structured data, quality of service index related data and the described sample areas set in period sample areas is corresponding.
In such scheme, described screening unit is in the sample data of described sample areas, and screening quality of service index is in zone of reasonableness, is positioned at the sample data set before percentage without line use ratio and Packet Data Channel PDCH load-carrying efficiency from high to low.
In such scheme, described data acquisition unit is treated assessment area by Gn signalling analysis system and is carried out customer service structured data statistics or the customer service structured data by historical data analysis prediction community future.
The network resource evaluation method based on customer service structure that the embodiment of the present invention provides and device, obtain the sample data of sample areas; Filter out qualified sample data according to network index, utilize mathematical modelling algorithm to carry out modeling qualified sample data, obtain the data model between Internet resources and customer service structure; Gather the customer service structured data in region to be assessed, bring the customer service structured data in described region to be assessed into described data model, draw the network resource data needed for described region to be assessed.So, can realize according to the accurate evaluation of user behavior to network resource consumption in mobile Internet, so become more meticulous for network resource optimization adjustment provides, the foundation of high reliability, improve resource utilization, avoid the irrational phenomenon of resource distribution.
Accompanying drawing explanation
Fig. 1 is the network resource evaluation method realization flow schematic diagram of the embodiment of the present invention based on customer service structure;
Fig. 2 is the composition structural representation of the embodiment of the present invention based on the network resource evaluation device of customer service structure;
Fig. 3 is that the embodiment of the present invention is for showing the hash figure of relation between customer service structured data and PDP maximum activation number;
Fig. 4 is wireless network resource consumption models accuracy analysis schematic diagram in embody rule example of the present invention.
Embodiment
In embodiments of the present invention, the sample data of sample areas is obtained; Filter out qualified sample data according to network index, utilize mathematical modelling algorithm to carry out modeling qualified sample data, obtain the data model between Internet resources and customer service structure; Gather the customer service structured data in region to be assessed, bring the customer service structured data in described region to be assessed into described data model, draw the network resource data needed for described region to be assessed.
Below in conjunction with drawings and the specific embodiments, the present invention is further described in more detail.
Fig. 1 is the network resource evaluation method realization flow schematic diagram of the embodiment of the present invention based on customer service structure, and as shown in Figure 1, the embodiment of the present invention comprises based on the network resource evaluation method of customer service structure:
Step S100: the sample data obtaining sample areas;
Particularly, the sample data of described acquisition sample areas comprises: to set granularity in units of the period, adds up the network resource data that the customer service structured data in this setting period sample areas, quality of service index related data and described sample areas are corresponding.
Here, the described setting period can be one hour, two hours of any initial time or arbitrarily needed for durations, such as: set the period as in two hours from 19:30, set the period as in three hours from 8:00 etc., the duration of concrete setting period can be determined according to the precision of required network resource evaluation.
Here, described sample areas can be a community, districts and cities or be the administrative coverage of certain equipment.
Here, described customer service structured data comprises: intelligent terminal accounting, instant messaging service number of users, instant messaging flow accounting, data service flow, voice telephone traffic amount and access point (Access Point Name, APN) accounting etc.;
Described quality of service index related data comprises: customer service success rate, user's access time delay, user's packet loss and user's average download rate etc.;
Described network resource data comprises: the data of radio network portion data, GPRS core net statistics and the data of WAP gateway system statistics; Wherein, described radio network portion data can be Packet Data Channel (Packet Data Channel, PDCH) load-carrying efficiency, on average take in number, Common Control Channel (Common Control Channel, CCCH) service request number and carrier frequency number one or more without line use ratio, PDCH; The data of described GPRS core net statistics can be one or more in SGSN Packet forwarding number, SGSN board average load, PDP maximum activation number; The data of described WAP gateway system statistics can be one or more in WAP gateway fire compartment wall session number, the maximum online user number of WAP gateway Radius.
Step S101: filter out qualified sample data according to network index;
Particularly, describedly screen qualified sample data according to network index and comprise: in all sample datas of described sample areas, screening quality of service index is in zone of reasonableness, is positioned at the sample data set before percentage without line use ratio and PDCH load-carrying efficiency from high to low; Wherein, quality of service index process zone of reasonableness be that customer service success rate is greater than a, user's access time delay is less than b, user's packet loss is less than c and user's average download rate higher than d.
Here, the concrete value of a, b, c, d can be determined according to the precision of required network resource evaluation.
Step S102: utilize mathematical modelling algorithm to carry out modeling qualified sample data, obtain the data model between Internet resources and customer service structure;
Here, for different Internet resources and customer service structure, different mathematical modelling algorithm can be adopted to carry out modeling, obtain different data models; Wherein, described mathematical modelling algorithm can be multivariate regression algorithm.Data model between any related network resource and customer service structure and other mathematical modelling algorithm adopted all belong to the scope that the present invention protects.
Step S103: the customer service structured data gathering region to be assessed;
Particularly, the customer service structured data in described collection region to be assessed comprises: treat assessment area by Gn signalling analysis system and carry out customer service structured data statistics or the customer service structured data by historical data analysis prediction community future.
Here, adopt as required and treat by Gn signalling analysis system the method that assessment area carries out customer service structured data statistics, can according to hour being unit granularity, gather and choose the maximum of customer service structured data in a day.
Step S104: bring the customer service structured data in described region to be assessed into described data model, draws the network resource data needed for described region to be assessed.
Fig. 2 is the composition structural representation of the embodiment of the present invention based on the network resource evaluation device of customer service structure, as shown in Figure 2, the embodiment of the present invention comprises based on the network resource evaluation device of customer service structure: data capture unit 10, screening unit 11, modeling unit 12, data acquisition unit 13 and computing unit 14; Wherein,
Described data capture unit 10, for obtaining the sample data of sample areas;
Particularly, described data capture unit 10, to set granularity in units of the period, adds up the network resource data that the customer service structured data in this setting period sample areas, quality of service index related data and described sample areas are corresponding.
Described screening unit 11, for filtering out qualified sample data according to network index;
Particularly, described screening unit 11 is in all sample datas of described sample areas, and screening quality of service index is in zone of reasonableness, is positioned at the sample data set before percentage without line use ratio and PDCH load-carrying efficiency from high to low.
Described modeling unit 12, for utilizing mathematical modelling algorithm to carry out modeling qualified sample data, obtains the data model between Internet resources and customer service structure;
Here, described mathematical modelling algorithm can be multivariate regression algorithm.
Described data acquisition unit 13, for gathering the customer service structured data in region to be assessed;
Particularly, described data acquisition unit 13 is treated assessment area by Gn signalling analysis system and is carried out customer service structured data statistics or the customer service structured data by historical data analysis prediction community future.
Described computing unit 14, for bringing the customer service structured data in described region to be assessed into described data model, draws the network resource data needed for described region to be assessed.
In actual applications, described data capture unit 10, screening unit 11, modeling unit 12, data acquisition unit 13 and computing unit 14 all can realize by being positioned at the central processing unit (CPU) of the webserver, microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA).
Specific embodiment one:
Be total flow to choose customer service structured data below, total number of users, intelligent terminal accounting, instant messaging flow accounting, network resource data is PDP maximum activation number, mathematical modelling algorithm is multivariate regression algorithm, in order to be treated assessment area by Gn signalling analysis system, to carry out customer service structured data statistics be example to the customer service structured data gathering region to be assessed, and the embodiment of the present invention specifically comprises based on the network resource evaluation method of customer service structure:
Step 1: granularity in units of per hour, adds up and obtains the total flow in sample areas per hour, total number of users, intelligent terminal accounting, instant messaging flow accounting, customer service success rate, user's access time delay, user's packet loss, user's average download rate and PDP maximum activation number equal samples data;
Step 2: screen rational sample data according to network index;
Particularly, for ensureing that Network resource allocation is reasonable and two conditions below the higher employing of resource utilization carry out sample data screening:
Condition (1): quality of service index is in zone of reasonableness, namely customer service success rate is greater than a, access time delay is less than b, user's packet loss is less than c, user's average download rate is higher than d;
Condition (2): in the data satisfying condition (1), screening is positioned at the sample data before 10%, as modeling data from high to low without line use ratio and PDCH load-carrying efficiency;
Step 3: utilize multivariate regression algorithm to carry out modeling qualified sample data, obtains the multivariate regression models between PDP maximum activation number and total flow, total number of users, intelligent terminal accounting, instant messaging flow accounting; This step specifically comprises:
1) relation between hash map analysis intelligent terminal accounting, instant messaging flow accounting, total flow, total number of users etc. and PDP maximum activation number is utilized;
Be illustrated in figure 3 the embodiment of the present invention for showing the hash figure of relation between customer service structured data and PDP maximum activation number.Wherein, the ordinate of Fig. 3 (a) ~ (d) is PDP maximum activation number, and abscissa is followed successively by total number of users, total flow (unit MB), instant messaging flow accounting, intelligent terminal accounting.
From analysis, total flow, always there is strong linear relationship between number of users and PDP maximum activation number, there is more weak linear relationship between intelligent terminal accounting and PDP maximum activation number, between instant messaging flow accounting and PDP maximum activation number, linear relationship is not obvious.
2) multivariate regression models between PDP maximum activation number and total flow, total number of users, intelligent terminal accounting, instant messaging flow accounting is determined;
Due to total flow, total number of users, between intelligent terminal accounting and PDP maximum activation number, all have linear relationship, therefore it is as follows to set up multiple linear regression model expression formula (1):
PDP maximum activation number=β
0+ β
1* intelligent terminal accounting+β
2* instant messaging flow accounting+β
3* total flow+β
4* total number of users (1)
3) qualified sample data step 2 filtered out is brought in above-mentioned model expression (1), minimum for principle with the error of calculation of PDP maximum activation number, obtains following model expression (2):
The PDP maximum activation number=-958376+539391* intelligent terminal accounting+2176841* instant messaging flow accounting-0.13485* total number of users of total flow-1.11339* (2)
4) detection validation is carried out to model expression (2);
Particularly, multiple linear regression detection method is utilized to judge this regression model expression formula (2):
If the degree of fitting R2 of this model expression (2) reaches 0.9929, then can think that the predicted value of this model and actual value are substantially identical, detection is passed through; If the error of calculation Distribution value of model expression (2) is not random number, then shows to there is non-linear relation between intelligent terminal accounting, instant messaging flow accounting, total flow, total number of users etc. and PDP maximum activation number, detect and do not pass through.Now, utilize box-cox to convert, non-linear relation is become linear relationship, bring sample data in data, obtain following model expression (3): 10
8/ PDP maximum activation number=β
0+ β
1* intelligent terminal accounting+β
2* instant messaging flow accounting+β
3* total flow+β
4* total number of users (3)
5) do not pass through, by repeating 3 if detected) and 4) step, finally can obtain there is following multivariate regression models between PDP maximum activation number and total flow, total number of users, intelligent terminal accounting and state formula (4): 10
8/ PDP maximum activation number=76.2-5.29* intelligent terminal accounting+8.21/10
7* instant messaging flow accounting-10
-5* total number of users (4)
Here, it should be noted that, other Internet resources relevant all can calculate in this way as PDCH on average takies number, CCCH service request number, SGSN cpu load, SGSN Packet forwarding number, WAP gateway fire compartment wall session number, the maximum online user number of WAP gateway Radius etc.
Step 4: by instruments such as Gn signalling analysis systems, according to hour being unit, gathers the maximum of the intelligent terminal accounting in region to be assessed in a day, the total customer service such as number of users and total flow structured data.
Step 5: the maximum of the customer service structured data obtained in step 4 is brought in step 3 in multivariate regression models statement formula (2) or (4) calculating acquisition, the demand of the Internet resources PDP maximum activation number in this region can be calculated.
It should be noted that, if the step 4 in above-mentioned flow process gathers is the predicted value of the future customer business structure data treating assessment area, then can calculate for this region to be assessed needed for future Internet resources PDP maximum activation number by step 5.
Specific embodiment two:
Below with Internet resources PDCH take number, CCCH service request number be evaluated as example, be illustrated the network resource evaluation method of the embodiment of the present invention based on customer service structure, concrete steps are as follows:
Step 10: by wireless webmaster data acquisition 1 month Bozhou area 4500 Duo Ge community network management data per hour and Gn signalling analysis system statistical data equal samples data;
Step 20: be greater than 99% for all sample datas according to the customer service success rate by community, user's access time delay be less than 5 seconds, user's packet loss be less than 5% and user's average download rate screen higher than 15Kbps, then filter out and be positioned at sample data before 30% from high to low without line use ratio and PDCH load-carrying efficiency, finishing screen selects 40W sample data.
Step 30: utilize multivariate regression algorithm to carry out data analysis and modeling for this 40W sample data, obtains following model expression (5), (6):
PDCH takies the number=7.537-15.63* intelligent terminal accounting+0.1924* instant message user number+0.1194* total number of users of total flow-0.0453* (5)
The CCCH service request number=7116.43-12635* intelligent terminal accounting+80.41* instant message user number+95.52* total number of users of total flow-50.63* (6)
Step 40: predict that certain zone user business structure data to be assessed is according to Gn signalling analysis system statistical data: intelligent terminal accounting 42.70%, instant message user number are 27603, total flow is 17930MB and total number of users is 70189.
Step 50: zone user business structure data to be assessed are brought into model expression (5) that step 30 draws, (6), is 380484 by calculating known PDCH to take number being 4273, CCCH service request number, only has 11.43% with actual error.
By above step 10 to 50, statistics draws Haozhou wireless network resource consumption models accuracy analysis schematic diagram, as shown in Figure 4.Wherein, abscissa representing time sequence, ordinate represents that PDCH takies number, and real, imaginary curve represents PDCH respectively and takies several actual values, and PDCH takies several predicted values.
Above disclosedly be only the implementation method of the example in the invention process method based on gsm wireless network, therefore every all network resource evaluation method relating to the statistics of wireless network core net etc. done according to the embodiment of the present invention, still belong to the scope that the present invention is contained.
The above, be only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.
Claims (10)
1. based on a network resource evaluation method for customer service structure, it is characterized in that, described method comprises:
Obtain the sample data of sample areas;
Filter out qualified sample data according to network index, utilize mathematical modelling algorithm to carry out modeling described qualified sample data, obtain the data model between Internet resources and customer service structure;
Gather the customer service structured data in region to be assessed, bring the customer service structured data in described region to be assessed into described data model, draw the network resource data needed for described region to be assessed.
2. method according to claim 1, is characterized in that, the sample data of described acquisition sample areas comprises:
To set granularity in units of the period, add up the network resource data that described customer service structured data, quality of service index related data and the described sample areas set in period sample areas is corresponding.
3. method according to claim 1 and 2, it is characterized in that, describedly screen qualified sample data according to network index and comprise: in the sample data of described sample areas, screening quality of service index is in zone of reasonableness, is positioned at the sample data set before percentage without line use ratio and Packet Data Channel PDCH load-carrying efficiency from high to low.
4. method according to claim 1 and 2, is characterized in that, described mathematical modelling algorithm is multivariate regression algorithm.
5. method according to claim 1 and 2, it is characterized in that, the customer service structured data in described collection region to be assessed comprises: treat assessment area by Gn signalling analysis system and carry out customer service structured data statistics or the customer service structured data by historical data analysis prediction community future.
6. based on a network resource evaluation device for customer service structure, it is characterized in that, described device comprises: data capture unit, screening unit, modeling unit, data acquisition unit and computing unit; Wherein,
Described data capture unit, for obtaining the sample data of sample areas;
Described screening unit, for filtering out qualified sample data according to network index;
Described modeling unit, for utilizing mathematical modelling algorithm to carry out modeling qualified sample data, obtains the data model between Internet resources and customer service structure;
Described data acquisition unit, for gathering the customer service structured data in region to be assessed;
Described computing unit, brings the customer service structured data in described region to be assessed into described data model, draws the network resource data needed for described region to be assessed.
7. device according to claim 6, it is characterized in that, described data capture unit, to set granularity in units of the period, adds up the network resource data that described customer service structured data, quality of service index related data and the described sample areas set in period sample areas is corresponding.
8. the device according to claim 6 or 7, it is characterized in that, described screening unit is in the sample data of described sample areas, and screening quality of service index is in zone of reasonableness, is positioned at the sample data set before percentage without line use ratio and Packet Data Channel PDCH load-carrying efficiency from high to low.
9. the device according to claim 6 or 7, is characterized in that, described mathematical modelling algorithm is multivariate regression algorithm.
10. the device according to claim 6 or 7, it is characterized in that, described data acquisition unit is treated assessment area by Gn signalling analysis system and is carried out customer service structured data statistics or the customer service structured data by historical data analysis prediction community future.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410086165.5A CN104901827B (en) | 2014-03-07 | 2014-03-07 | A kind of network resource evaluation method and device based on customer service structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410086165.5A CN104901827B (en) | 2014-03-07 | 2014-03-07 | A kind of network resource evaluation method and device based on customer service structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104901827A true CN104901827A (en) | 2015-09-09 |
| CN104901827B CN104901827B (en) | 2019-02-15 |
Family
ID=54034231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410086165.5A Active CN104901827B (en) | 2014-03-07 | 2014-03-07 | A kind of network resource evaluation method and device based on customer service structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104901827B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107566207A (en) * | 2017-08-07 | 2018-01-09 | 北京天元创新科技有限公司 | The appraisal procedure and device of a kind of network resource consumption |
| CN107734534A (en) * | 2016-08-10 | 2018-02-23 | 中国移动通信集团黑龙江有限公司 | A kind of network load appraisal procedure and device |
| CN108764960A (en) * | 2018-04-12 | 2018-11-06 | 合肥天源迪科信息技术有限公司 | A kind of IN service decision system and method based on big data analysis |
| CN109905271A (en) * | 2018-05-18 | 2019-06-18 | 华为技术有限公司 | A kind of prediction technique, training method, device and computer storage medium |
| CN110475255A (en) * | 2018-05-10 | 2019-11-19 | 中国移动通信集团浙江有限公司 | Network load prediction technique and device |
| CN112055380A (en) * | 2019-06-06 | 2020-12-08 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
| CN112511324A (en) * | 2019-09-16 | 2021-03-16 | 中国移动通信集团河北有限公司 | Big data-based user satisfaction evaluation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101771758A (en) * | 2008-12-31 | 2010-07-07 | 北京亿阳信通软件研究院有限公司 | Dynamic determine method for normal fluctuation range of performance index value and device thereof |
| CN101883014A (en) * | 2010-07-22 | 2010-11-10 | 中兴通讯股份有限公司 | Method and system for acquiring performance statistical data |
| US20120203788A1 (en) * | 2009-10-16 | 2012-08-09 | Magyar Gabor | Network management system and method for identifying and accessing quality of service issues within a communications network |
| CN103167505A (en) * | 2011-12-19 | 2013-06-19 | 中国移动通信集团福建有限公司 | Method and system of neighborhood data channel configuration |
| CN103491556A (en) * | 2012-06-13 | 2014-01-01 | 华为技术服务有限公司 | Method and device for network adjustment |
-
2014
- 2014-03-07 CN CN201410086165.5A patent/CN104901827B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101771758A (en) * | 2008-12-31 | 2010-07-07 | 北京亿阳信通软件研究院有限公司 | Dynamic determine method for normal fluctuation range of performance index value and device thereof |
| US20120203788A1 (en) * | 2009-10-16 | 2012-08-09 | Magyar Gabor | Network management system and method for identifying and accessing quality of service issues within a communications network |
| CN101883014A (en) * | 2010-07-22 | 2010-11-10 | 中兴通讯股份有限公司 | Method and system for acquiring performance statistical data |
| CN103167505A (en) * | 2011-12-19 | 2013-06-19 | 中国移动通信集团福建有限公司 | Method and system of neighborhood data channel configuration |
| CN103491556A (en) * | 2012-06-13 | 2014-01-01 | 华为技术服务有限公司 | Method and device for network adjustment |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107734534A (en) * | 2016-08-10 | 2018-02-23 | 中国移动通信集团黑龙江有限公司 | A kind of network load appraisal procedure and device |
| CN107734534B (en) * | 2016-08-10 | 2020-10-30 | 中国移动通信集团黑龙江有限公司 | Network load evaluation method and device |
| CN107566207A (en) * | 2017-08-07 | 2018-01-09 | 北京天元创新科技有限公司 | The appraisal procedure and device of a kind of network resource consumption |
| CN108764960A (en) * | 2018-04-12 | 2018-11-06 | 合肥天源迪科信息技术有限公司 | A kind of IN service decision system and method based on big data analysis |
| CN110475255A (en) * | 2018-05-10 | 2019-11-19 | 中国移动通信集团浙江有限公司 | Network load prediction technique and device |
| CN110475255B (en) * | 2018-05-10 | 2022-04-05 | 中国移动通信集团浙江有限公司 | Network load prediction method and device |
| CN109905271A (en) * | 2018-05-18 | 2019-06-18 | 华为技术有限公司 | A kind of prediction technique, training method, device and computer storage medium |
| WO2019219052A1 (en) * | 2018-05-18 | 2019-11-21 | 华为技术有限公司 | Prediction method, training method, apparatus, and computer storage medium |
| CN109905271B (en) * | 2018-05-18 | 2021-01-12 | 华为技术有限公司 | Prediction method, training method, device and computer storage medium |
| CN112055380A (en) * | 2019-06-06 | 2020-12-08 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
| CN112055380B (en) * | 2019-06-06 | 2022-04-29 | 华为技术有限公司 | Method and apparatus for predicting traffic volume |
| CN112511324A (en) * | 2019-09-16 | 2021-03-16 | 中国移动通信集团河北有限公司 | Big data-based user satisfaction evaluation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104901827B (en) | 2019-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104901827A (en) | Network resource evaluation method and device based on user business structure | |
| CN106301984B (en) | A kind of mobile communications network capacity prediction methods and device | |
| CN105392154A (en) | Resource occupation prediction method and system | |
| CN105101302B (en) | Flow managing method and system based on user's use habit | |
| WO2016086406A1 (en) | Network resource deployment method and device | |
| CN104113872B (en) | A kind of method for monitoring data traffic and system | |
| CN103686745A (en) | Method and device for optimizing frequency in LTE system | |
| CN103906027A (en) | User value evaluation method and system based on mobile user internet surfing behaviors | |
| CN103209422A (en) | Method for accurate spot selection of wireless local area network (WLAN) | |
| CN107276799A (en) | Mobile terminal method for predicting and device | |
| CN105636056A (en) | Spectrum resource self-optimization energy-saving method, apparatus and system | |
| CN105205878A (en) | Inspection method and system of water drainage pipe net | |
| CN104093197A (en) | Equipment energy saving method and system applied to mobile internet | |
| CN106714223B (en) | Method and device for establishing base station energy consumption model | |
| CN104683182A (en) | Method and device for detecting network service quality of IDC machine room | |
| CN102883352A (en) | GSM (global system for mobile communications) cell parameter optimization method based on traffic modeling and traffic prediction | |
| CN102761889A (en) | Method and system for evaluating wireless network structure | |
| CN105874843A (en) | Data transmission method according to battery use pattern | |
| CN101931986B (en) | Indication method of network energy efficiency, indicator and system | |
| CN102111888B (en) | Channel allocation method and device and system | |
| CN107846614B (en) | Video traffic scheduling method and device and electronic equipment | |
| CN109995549A (en) | A kind of method and device for assessing Flow Value | |
| CN107155192B (en) | User experience quality assessment method and device | |
| CN112969193B (en) | Interference determination method, device and equipment for wireless network | |
| Wietfeld et al. | Resource efficient mobile communications for crowd-sensing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |